AL
Aryo Lotfi
cs.LGcs.AIstat.MLcs.CLcs.CV
On Valency
published · living versionsW_3r3u6gpt·v1 · currentpublished
Weighted State Souping for Efficient Long-Context Retrieval
with William L. Tong, Emmanuel Abbe, Josh Susskind, Cengiz Pehlevan +1
1 version
Preprints & journals
12 papers in the corpus · 2022–2026Weighted State Souping for Efficient Long-Context Retrieval2610.25621v1 · William L. Tong, Aryo Lotfi, Emmanuel Abbe et al.2026 · 0 citationsarXivon Valency
RLTLDR: Self-improvement by Internalizing Self-generated Feedback2609.37633v2 · Michael Kirchhof, Eleonora Gualdoni, Andrew Szot et al.2026 · 0 citationsarXiv
On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models2609.16540v1 · William L. Tong, Aryo Lotfi, Emmanuel Abbe et al.2026 · 0 citationsarXiv
Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve2608.03550v1 · Denys Pushkin, Albert Q. Jiang, Aryo Lotfi et al.2026 · 0 citationsarXiv
Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning2602.14868v3 · Ilia Mahrooghi, Aryo Lotfi, Emmanuel Abbe2026 · 0 citationsarXiv
To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models2510.14826v1 · Eran Malach, Omid Saremi, Sinead Williamson et al.2025 · 0 citationsarXiv
RL for Reasoning by Adaptively Revealing Rationales2506.18110v2 · Mohammad Hossein Amani, Aryo Lotfi, Nicolas Mario Baldwin et al.2025 · 0 citationsarXiv
Chain-of-Sketch: Enabling Global Visual Reasoning2410.08165v2 · Aryo Lotfi, Enrico Fini, Samy Bengio et al.2024 · 0 citationsarXiv
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad2406.06467v3 · Emmanuel Abbe, Samy Bengio, Aryo Lotfi et al.2024 · 1 citationarXiv
Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs2306.16921v1 · Emmanuel Abbe, Elisabetta Cornacchia, Aryo Lotfi2023 · 7 citationsarXiv
Generalization on the Unseen, Logic Reasoning and Degree Curriculum2301.13105v3 · Emmanuel Abbe, Samy Bengio, Aryo Lotfi et al.2023 · 4 citationsarXiv
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures2205.13647v2 · Emmanuel Abbe, Samy Bengio, Elisabetta Cornacchia et al.2022 · 2 citationsarXiv
Career total: 12 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.